Yellow River Delta wetlands are essential for the migration of endangered birds and breeding. The wetlands, however, have been severely damaged during recent decades, partly due to the lack of wetland ecosystem protection by authorities. To have a better historical understanding of the spatio-temporal dynamics of the wetlands, this study aims to map and characterize patterns of the loss and degradation of wetlands in the Yellow River Delta using a time series of remotely sensed images (at nine points in time) based on object-based image analysis and knowledge transfer learning technology. Spatio-temporal analysis was conducted to document the long-term changes taking place in different wetlands over the four decades. The results showed that the Yellow River Delta wetlands have experienced significant changes between 1973 and 2013. The total area of wetlands has been reduced by 683.12 km² during the overall period and the trend of loss continues. However, the rates and trends of change for the different types of wetlands were not the same. The natural wetlands showed a statistically significant decrease in area during the overall period (36.04 km²·year⁻¹). Meanwhile, the artificial wetlands had the opposite trend and showed a statistically significant increase in area during the past four decades (18.96 km²·year⁻¹). According to the change characteristics revealed by the time series wetland classification maps, the evolution process of the Yellow River Delta wetlands could be divided into three stages: (1) From 1973–1984, basically stable, but with little increase; (2) from 1984–1995, rapid loss; and (3) from 1995–2013, slow loss. The area of the wetlands reached a low point around 1995, and then with a little improvement, the regional wetlands entered a slow loss stage. It is believed that interference by human activities (e.g., urban construction, cropland creation, and oil exploitation) was the main reason for wetland degradation in the Yellow River Delta over the past four decades. Climate change also has long-term impacts on regional wetlands. In addition, due to the special geographical environment, the hydrological and sediment conditions and the location of the Yellow River mouth also have a significant influence on the evolution process of the wetlands.

Net ecosystem productivity (NEP) is an important indicator for estimating regional carbon sources/sinks. The study focuses on a comprehensive computational simulation and spatiotemporal variation study of the NEP in the Yellow River basin from 2000 to 2020 using NPP data products from MODIS combined with a quantitative NEP estimation model followed by a comprehensive analysis of the spatiotemporal variation characteristics and dynamic procession persistence analysis based on meteorological data and land use data. The results show that: (1) The total NEP in the Yellow River basin had an overall increasing trend from 2000 to 2020, with a Theil–Sen trend from −23.37 to 43.66 gCm⁻²a⁻¹ and a mean increase of 4.64 gCm⁻²a⁻¹ (p < 0.01, 2-tailed). (2) Most areas of the Yellow River basin are carbon sink areas, and the annual average NEP per unit area was 208.56 gCm⁻²a⁻¹ from 2000 to 2020. There were, however, substantial spatial and temporal variations in the NEP. Most of the carbon source area was located in the Kubuqi Desert and its surroundings. (3) Changes in land use patterns were the main cause of changes in regional NEP. During the 2000–2020 period, 1154.24 t of NEP were added, mainly due to changes in land use, e.g., the conversion of farmland to forests and grasslands. (4) The future development in 83.43% of the area is uncertain according to the Hurst index dynamic persistence analysis. In conclusion, although the carbon−sink capacity of the terrestrial ecosystem in the Yellow River basin is increasing and the regional carbon sink potential is increasing in the future, the future development of new energy resources has regional uncertainties, and the stability of the basin ecosystem needs to be enhanced.

Mapping cropland distribution over large areas has attracted great attention in recent years, however, traditional pixel-based classification approaches produce high uncertainty in cropland area statistics. This study proposes a new approach to map fractional cropland distribution in Mato Grosso, Brazil using time series MODIS enhanced vegetation index (EVI) and Landsat Thematic Mapper (TM) data. The major steps include: (1) remove noise and clouds/shadows contamination using the Savizky–Gloay filter and temporal resampling algorithm based on the time series MODIS EVI data; (2) identify the best periods to extract croplands through crop phenology analysis; (3) develop a seasonal dynamic index (SDI) from the time series MODIS EVI data based on three key stages: sowing, growing, and harvest; and (4) develop a regression model to estimate cropland fraction based on the relationship between SDI and Landsat-derived fractional cropland data. The root mean squared error of 0.14 was obtained based on the analysis of randomly selected 500 sample plots. This research shows that the proposed approach is promising for rapidly mapping fractional cropland distribution in Mato Grosso, Brazil.